List files under data/<domain>, RBAC-enforced.
AI agents call list_files to retrieve information from FinRAG-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries file metadata with no side effects. It creates no data, modifies nothing, executes no external operations, and deletes nothing. Role-based access control mitigates the blast radius of misuse—an agent can only list files the assigned role permits. Listing files is a read-only, low-risk operation typical of a secure document retrieval system.
From the tool's definition Tool name 'list_files' and description 'List files under data/<domain>' indicate a retrieval operation. The phrase 'RBAC-enforced' confirms access controls prevent unauthorized data visibility across departments.
Attacks that exploit this kind of access
List files under data/<domain>, RBAC-enforced. It is categorised as a Read tool in the FinRAG-MCP MCP Server, which means it retrieves data without modifying state.
Register the FinRAG- MCP server in PolicyLayer and add a rule for list_files: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches FinRAG-MCP. Nothing to install.
list_files is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_files rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_files. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_files is provided by the FinRAG- MCP server (nithishkaranam2002/finrag--mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →